Remote maintenance method based on distributed experimental equipment and related equipment

Abstract

The invention belongs to the field of data processing, and particularly relates to a remote maintenance method based on distributed experimental equipment and related equipment, and the method comprises the steps: obtaining equipment operation data of target equipment in a distributed experimental equipment management and control system in response to a monitoring instruction for the distributed experimental equipment management and control system; inputting the equipment operation data into the fault intelligent diagnosis model to execute abnormal mode recognition of the target equipment so as to obtain a potential abnormal mode matched with the target equipment; determining equipment circulation control information of the distributed experimental equipment management and control system based on the potential abnormal mode; generating abnormal alarm information of the target equipment based on the equipment circulation control information, and sending the abnormal alarm information to a user at the remote client side; and in response to a remote maintenance instruction fed back for the abnormal alarm information, executing remote maintenance operation matched with the remote maintenance instruction on the target equipment. The remote maintenance efficiency of distributed experimental equipment can be improved, the operation risk of the system is reduced, and the stability and reliability of the system are enhanced.

Description

Technical Field

[0001] The present application belongs to the field of data processing, and in particular, relates to a remote maintenance method based on distributed experimental equipment and related equipment. Background Art

[0002] In order to promote the popularization of intelligent applications in various industries and fields, distributed experimental equipment generates a large amount of data.

[0003] In the related art, many different types of experimental equipment are deployed in the laboratory, and each device may have different usage and maintenance requirements. The diversity and complexity of this equipment makes remote maintenance difficult, especially when multiple devices need to be updated and monitored simultaneously. In addition, experimental equipment often requires high-cost maintenance and regular inspections. Failure to detect or deal with equipment problems in a timely manner may result in expensive repair or replacement costs, as well as loss of experimental data.

[0004] Therefore, it is urgent to design a remote maintenance solution based on distributed experimental equipment to solve at least one of the above technical problems. Summary of the invention

[0005] The present application provides a remote maintenance method and related equipment based on distributed experimental equipment to improve the remote maintenance efficiency of distributed experimental equipment, timely discover potential risk patterns in the system, reduce system operation risks, and enhance system stability and reliability.

[0006] In a first aspect, the present application provides a remote maintenance method based on distributed experimental equipment, which is applied to a distributed experimental equipment management and control system, wherein the distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment; the remote maintenance method based on distributed experimental equipment includes:

[0007] In response to a monitoring instruction for the distributed experimental equipment control system, obtaining equipment operation data of a target equipment in the distributed experimental equipment control system;

[0008] Inputting the equipment operation data into the fault intelligent diagnosis model to perform abnormal pattern recognition on the target equipment to obtain potential abnormal patterns matching the target equipment;

[0009] Based on the potential abnormal pattern, determine the equipment flow control information of the distributed experimental equipment management and control system;

[0010] Generate abnormal alarm information of the target device based on the device flow control information, and send it to the user on the remote client side;

[0011] In response to the remote maintenance instruction fed back in response to the abnormal alarm information, a remote maintenance operation matching the remote maintenance instruction is performed on the target device.

[0012] In a second aspect, an embodiment of the present application provides a distributed experimental equipment management and control system, the distributed experimental equipment management and control system is used to operate and manage experimental equipment, the experimental equipment includes different types of equipment, and the distributed experimental equipment management and control system includes:

[0013] A monitoring unit, configured to obtain device operation data of a target device in the distributed experimental device control system in response to a monitoring instruction for the distributed experimental device control system;

[0014] an identification unit configured to input the device operation data into a fault intelligent diagnosis model to perform abnormal pattern identification on the target device to obtain a potential abnormal pattern matching the target device;

[0015] A circulation unit, configured to determine the equipment circulation control information of the distributed experimental equipment management and control system based on the potential abnormal mode;

[0016] an alarm unit, configured to generate abnormal alarm information of a target device based on the device flow control information, and send the information to a user at a remote client side;

[0017] The maintenance unit is configured to respond to the remote maintenance instruction fed back to the abnormal alarm information and execute a remote maintenance operation matching the remote maintenance instruction on the target device.

[0018] In a third aspect, an embodiment of the present application provides an intelligent computing platform, the intelligent computing platform comprising:

[0019] at least one processor, memory, and input-output unit;

[0020] Among them, the memory is used to store computer programs, the processor is used to call the computer program stored in the memory to execute the remote maintenance method based on distributed experimental equipment in the first aspect, and the input and output unit is used to receive user input and display output information of the computer program stored in the memory.

[0021] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions. When the instructions are executed on a computer, the computer executes the remote maintenance method based on distributed experimental equipment in the first aspect.

[0022] The technical solution provided in the embodiment of the present application can be applied to a distributed experimental equipment control system. The distributed experimental equipment control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment. In this solution, first, in response to the monitoring instruction of the distributed experimental equipment control system, the equipment operation data of the target equipment in the distributed experimental equipment control system is obtained. Here, a data basis is provided for subsequent intelligent detection and remote maintenance, which helps to timely discover potential abnormal patterns and warn of possible problems in advance, thereby reducing the occurrence of equipment failures and reducing maintenance costs. Then, the equipment operation data is input into the fault intelligent diagnosis model to perform abnormal pattern recognition of the target equipment to obtain the potential abnormal pattern matching the target equipment. In this way, the process and control strategy of the equipment can be automatically adjusted based on the abnormal pattern to reduce the risk of failure and improve the utilization and efficiency of the equipment. Then, based on the potential abnormal pattern, the equipment flow control information of the distributed experimental equipment control system is determined. This helps to improve the accuracy and reliability of potential abnormal pattern recognition and reduce the influence of subjective factors on equipment management and maintenance. Furthermore, abnormal alarm information of the target equipment is generated based on the equipment flow control information and sent to the user on the remote client side. Finally, in response to the remote maintenance instruction for the abnormal alarm information feedback, the remote maintenance operation matching the remote maintenance instruction is performed on the target device. The abnormal situation can be obtained in time and corresponding measures can be taken to improve the reliability and safety of equipment operation. At the same time, performing remote maintenance operations in response to remote maintenance instructions can effectively reduce maintenance response time and improve maintenance efficiency.

[0023] The technical solution of this application, through operations such as intelligent fault diagnosis models, equipment flow control and remote maintenance, helps to realize the intelligent and real-time management of distributed experimental equipment control systems, improve the remote maintenance efficiency of distributed experimental equipment, timely discover potential risk patterns in the system, reduce system operation risks, enhance system stability and reliability, reduce maintenance costs, and provide users with better user experience and service support. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0025] Figure 1 It is a flow chart of a remote maintenance method based on distributed experimental equipment according to an embodiment of the present application;

[0026] Figure 2 It is a structural schematic diagram of a distributed experimental equipment control system according to an embodiment of the present application;

[0027] Figure 3 It is a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0030] In order to promote the popularization of intelligent applications in various industries and fields, distributed experimental equipment generates a large amount of data.

[0031] In the related art, many different types of experimental equipment are deployed in the laboratory, and each device may have different usage and maintenance requirements. The diversity and complexity of this equipment makes remote maintenance difficult, especially when multiple devices need to be updated and monitored simultaneously. In addition, experimental equipment often requires high-cost maintenance and regular inspections, and failure to detect or deal with equipment problems in a timely manner may result in expensive repair or replacement costs, as well as loss of experimental data.

[0032] Therefore, it is urgent to design a remote maintenance solution based on distributed experimental equipment to solve at least one of the above technical problems.

[0033] The embodiments of the present application provide a remote maintenance method based on distributed experimental equipment and related equipment.

[0034] Specifically, the remote maintenance scheme based on distributed experimental equipment can be applied to the distributed experimental equipment management and control system. The distributed experimental equipment management and control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment. In this scheme, first, in response to the monitoring instruction of the distributed experimental equipment management and control system, the equipment operation data of the target equipment in the distributed experimental equipment management and control system is obtained. Here, a data basis is provided for subsequent intelligent detection and remote maintenance, which helps to timely discover potential abnormal patterns and warn of possible problems in advance, thereby reducing the occurrence of equipment failures and reducing maintenance costs. Then, the equipment operation data is input into the fault intelligent diagnosis model to perform abnormal pattern recognition of the target equipment to obtain the potential abnormal pattern matching the target equipment. In this way, the process and control strategy of the equipment can be automatically adjusted based on the abnormal pattern to reduce the risk of failure and improve equipment utilization and efficiency. Then, based on the potential abnormal pattern, the equipment flow control information of the distributed experimental equipment management and control system is determined. This helps to improve the accuracy and reliability of potential abnormal pattern recognition and reduce the influence of subjective factors on equipment management and maintenance. Furthermore, abnormal alarm information of the target equipment is generated based on the equipment flow control information and sent to the user on the remote client side. Finally, in response to the remote maintenance instruction for the abnormal alarm information feedback, the remote maintenance operation matching the remote maintenance instruction is performed on the target device. The abnormal situation can be obtained in time and corresponding measures can be taken to improve the reliability and safety of equipment operation. At the same time, performing remote maintenance operations in response to remote maintenance instructions can effectively reduce maintenance response time and improve maintenance efficiency.

[0035] In the remote maintenance solution based on distributed experimental equipment, through intelligent fault diagnosis models, equipment flow control and remote maintenance operations, it helps to realize the intelligent and real-time management of distributed experimental equipment control systems, improve the remote maintenance efficiency of distributed experimental equipment, and timely discover potential risk patterns in the system, reduce system operation risks, enhance system stability and reliability, reduce maintenance costs, and provide users with better user experience and service support.

[0036] The remote maintenance scheme based on distributed experimental equipment provided in the embodiment of the present application can also be performed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a special device (such as a special terminal device with a remote maintenance system based on distributed experimental equipment). The chips introduced in the above embodiments can also be carried in these electronic devices. Alternatively, these electronic devices can also be installed with a service program for executing a remote maintenance scheme based on distributed experimental equipment.

[0037] Figure 1A schematic diagram of a remote maintenance method based on distributed experimental equipment provided in an embodiment of the present application is shown in FIG. Figure 1 , the method comprises the following steps:

[0038] 101. In response to a monitoring instruction for the distributed experimental equipment management and control system, obtain equipment operation data of a target equipment in the distributed experimental equipment management and control system.

[0039] In the embodiment of the present application, the distributed experimental equipment management and control system is used to operate and manage experimental equipment. These experimental equipment include different types of equipment.

[0040] In the embodiment of the present application, the remote maintenance method based on the distributed test equipment safety management system involves a relatively complex system architecture, which needs to fully consider the communication, data transmission, security and other aspects between the server and the client. The following is an introduction to the technical background of the system and related equipment:

[0041] Further optionally, the distributed test equipment safety management and control system is designed based on the C / S architecture. The C / S architecture refers to the client / server architecture, which separates the user interface and the application logic. The user communicates with the server through the client, and the server processes the request and returns the result. This architecture is usually used for applications that require complex logic processing and large amounts of data storage. The microservice architecture is an architectural pattern that splits an application into a series of small, independently deployed services. Each microservice can be independently developed, deployed, and expanded, and communicates through a lightweight communication protocol, thereby achieving a highly cohesive and low-coupling system architecture. QT is a cross-platform C++ application development framework that can be used to develop graphical user interface applications. It provides a wealth of GUI components and tools that can simplify the development process of cross-platform applications while having good performance and scalability. Distributed test equipment refers to test equipment deployed at different locations or nodes, which can collaborate with each other to complete test tasks and communicate and exchange data through the network. Distributed test equipment is usually highly flexible and scalable, and can be dynamically configured and deployed as needed. The server is the core of the entire system, responsible for the implementation of various functional modules and data processing tasks. In this system, the server adopts a microservice architecture design, which includes multiple independent functional modules, such as operation status monitoring, audit log collection and analysis, ledger management, resource management, etc. Each functional module can be deployed and expanded independently, and interact through a lightweight communication mechanism. The client is the interface for users to interact with the system, responsible for receiving user input, displaying information and sending requests to the server. In this system, the client is developed based on QT and includes functional modules such as user authentication, equipment management, information management, test parameter management, file management, software management, and remote control. The client realizes the interaction and remote maintenance between users and the system through communication with the server. In summary, the remote maintenance method based on the distributed test equipment safety management and control system combines C / S architecture, microservice architecture and QT development technology, realizes real-time management and intelligent control of distributed test equipment, and provides strong support for the safety, stability and reliability of test equipment.

[0042] As an optional embodiment, in step 101, in response to a monitoring instruction for the distributed experimental equipment control system, obtaining the equipment operation data of the target equipment in the distributed experimental equipment control system may be implemented as follows:

[0043] 201, obtaining an experimental task matched with a target device in the distributed experimental device management and control system; wherein experimental tasks matched with different types of devices have different task requirements;

[0044] 202, based on the task requirements of the target device, construct a device remote control task corresponding to the target device through a dynamic control model; wherein the device remote control task is used to assist the target device in achieving the experimental task;

[0045] 203, synchronizing the device remote control task to the target device in the distributed experimental device control system, and receiving a monitoring instruction generated by the target device in response to the device remote control task;

[0046] 204 , based on the monitoring instruction, collecting the device operation data of the target device in the process of executing the experimental task in real time.

[0047] Specifically, in 201, by obtaining the experimental tasks that match the target device, it can ensure that different types of equipment are managed and controlled according to their task requirements. The experimental task requirements of different devices may be different, and accurate matching of experimental tasks helps to improve the efficiency and reliability of equipment operation. In 202, based on the task requirements of the target device, a dynamic control model is constructed to realize targeted equipment remote control tasks. The task model designed in this way can better assist the target device to complete the experimental tasks and improve the efficiency and accuracy of the experiment. In 203, the remote control task of the synchronized device is sent to the target device, so that the system can monitor and control the operation of the device in real time, and improve the accuracy and real-time performance of the control. At the same time, receiving the monitoring instructions responded by the device helps to obtain feedback information and adjust the control strategy in time. In 204, the equipment operation data of the target device in the execution of the experimental task is collected in real time based on the monitoring instructions, which helps to fully understand the operating status, performance and possible abnormal conditions of the equipment. In this way, problems can be discovered early and corresponding measures can be taken to ensure the smooth progress of the experimental tasks.

[0048] Through 201 to 204, the steps of experimental task matching, dynamic control model construction, equipment remote control task synchronization and real-time data collection are realized, providing a more efficient and intelligent distributed experimental equipment control system management method. Accurately matching experimental tasks, building control models in a targeted manner, real-time monitoring and regulating equipment operations, fully understanding equipment status and responding to abnormal situations in a timely manner will help improve the efficiency and reliability of equipment operation, realize refined and automated equipment control, and provide users with better experimental experience and service support.

[0049] In the embodiment of the present application, the dynamic control model is a control model that is dynamically adjusted according to the real-time data and system status changes. In the distributed experimental equipment control system, the dynamic control model can dynamically adjust the remote control tasks of the equipment according to the task requirements and real-time conditions of the target equipment to ensure that the equipment can effectively complete the predetermined tasks and adapt to the changing working environment.

[0050] Optionally, the dynamic control model is updated and adjusted based on real-time feedback data and monitoring instructions to ensure that the model is consistent with the actual status of the target device. By continuously collecting equipment operation data, analyzing equipment performance indicators, and monitoring equipment status changes, the dynamic control model can promptly identify problems and challenges in equipment operation and adjust remote control tasks accordingly to improve the adaptability, stability, and efficiency of the system.

[0051] The key to the dynamic control model is that it can respond to changes in equipment status and task requirements in a timely manner, and realize real-time control decisions and operational guidance. By implementing the dynamic control model, the distributed experimental equipment control system can better adapt to complex working environments and task requirements, improve the operating efficiency, reliability and flexibility of the equipment, and thus provide users with a better service experience.

[0052] As an optional example, assume that the dynamic control model includes at least the following structures: feature recognition layer, feature fusion layer, and dynamic construction layer. Based on this, the task requirements of the target device and the construction of the device remote control task corresponding to the target device through the dynamic control model can be implemented as the following process:

[0053] Through the feature recognition layer, the operation and maintenance requirement features of the target device are extracted from the task requirements of the target device;

[0054] Through the feature fusion layer, multi-dimensional feature fusion and conflict detection are performed on the operation and maintenance demand features of the target equipment to obtain the comprehensive operation and maintenance features of the target equipment;

[0055] Through the feature fusion layer, based on the pre-established control task components and the spatial mapping relationship between the task components and the demand dimensions, the comprehensive operation and maintenance characteristics of the target device are dynamically constructed to obtain the remote control tasks of the target device.

[0056] In a distributed experimental equipment management scenario, the structure of the dynamic control model can be used to build a system with intelligent control capabilities to achieve remote monitoring and control of each experimental equipment. In this scenario, each experimental equipment may have different operation and maintenance requirements, such as equipment status, usage frequency, energy consumption, etc. The feature recognition layer can extract these features from the monitoring data of each experimental equipment, such as equipment online status, temperature, humidity, energy consumption and other information. The feature fusion layer fuses the multi-dimensional features extracted from each experimental equipment, such as fusing the real-time status information of the equipment with the historical data and usage rules of the equipment, and detects the conflicts between possible features to ensure the accuracy of the comprehensive features. Based on the pre-established control task components and the spatial mapping relationship between the task components and the demand dimensions, the comprehensive operation and maintenance features are processed in the dynamic construction layer to dynamically construct remote control tasks. For example, according to the comprehensive characteristics of each experimental equipment and the experimental progress, the operating parameters or modes of the experimental equipment are dynamically adjusted to improve the equipment utilization and experimental efficiency. Through this dynamic control model, intelligent remote management and control of distributed experimental equipment can be realized, and the control strategy can be dynamically adjusted according to real-time data and needs to improve the utilization and efficiency of equipment while reducing management costs. This intelligent management and control system can be applied to various scenarios such as laboratory management and industrial production, providing users with more intelligent and efficient management solutions.

[0057] For example, a dynamic control model based on fuzzy logic control is used to realize a virtual control system for the temperature of a distributed experimental equipment. Assume that the input is the difference between the current temperature and the desired temperature, and the output is the control force of heating or cooling. The dynamic control model consists of three main parts: fuzzification (definition of fuzzy sets), fuzzy rule base, and defuzzification (fuzzy output is defuzzified into actual control force).

[0058] The first step is fuzzification: the input variable is, for example, the deviation (e), which is the difference between the current temperature and the expected temperature. The deviation can be divided into three fuzzy sets: negative deviation (NB, Negative Big), zero deviation (ZE, Zero Error), and positive deviation (PB, Positive Big). The output variable is, for example, the control force (Δu), that is, the control force can be divided into three fuzzy sets: cooling (CO, Cooling), unchanged (NO, No change), and heating (HE, Heating). The second step is the fuzzy rule base, for example, based on experience and rules to define the relationship between the deviation and the control force. For example, Rule 1: IF e is PB THEN Δu is CO; Rule 2: IF e is ZE THEN Δu is NO; Rule 3: IF e is NB THEN Δu is HE. The third step is defuzzification, for example, the control force obtained according to the fuzzy rule base is defuzzified, and the final control force can be obtained by methods such as weighted average method. This is a dynamic management and control model based on fuzzy logic control. In practical applications, it is necessary to design fuzzy sets, rule bases and defuzzification methods according to specific problems and system characteristics in order to achieve effective control of the system.

[0059] 102 , input the device operation data into a fault intelligent diagnosis model to perform abnormal pattern recognition on the target device to obtain a potential abnormal pattern matching the target device.

[0060] As an optional embodiment, it is assumed that the intelligent fault diagnosis model includes at least the following structures: a data preprocessing layer, a fault feature extraction layer, an adaptive control layer, and an abnormal pattern recognition layer.

[0061] Based on the above model structure, in 102, the device operation data is input into the fault intelligent diagnosis model to perform abnormal pattern recognition on the target device to obtain the potential abnormal pattern matching the target device, which can be implemented as follows:

[0062] 301, preprocessing the device operation data through a data preprocessing layer; the preprocessing at least includes: data cleaning, data normalization, and data smoothing;

[0063] 302, extracting statistical features, frequency domain features, and time domain features from the device operation data through a fault feature extraction layer, and fusing them into fault analysis features;

[0064] 303, through the adaptive control layer, according to the real-time monitoring of equipment status and environmental changes, dynamically adjust the model parameters and operation strategies of the abnormal pattern recognition layer to adapt to different equipment working conditions and corresponding failure modes;

[0065] 304 , performing pattern recognition on the fault analysis feature based on an adaptive recognition strategy through an abnormal pattern recognition layer to obtain potential abnormal pattern information of the target device.

[0066] In the embodiment of the present application, the potential abnormal pattern information is used to indicate the candidate abnormal behavior of the target device. For example, the potential abnormal pattern information is used to indicate the candidate abnormal behavior of the target device, which can help identify possible faults or abnormal conditions of the device, so as to perform preventive maintenance or fault diagnosis. The following are some examples of possible potential abnormal pattern information: 1. Abnormal waveform shape: The waveform data collected by the device sensor has a special shape in certain time periods, which is different from the waveform shape during normal operation, which may indicate that some components of the device are faulty. 2. Frequency change: When the device is running, some frequency components have abnormal changes, which may indicate that the vibration frequency of some components has changed, which may be caused by wear or looseness. 3. Step response abnormality: When the device is subjected to external stimulation or input signal changes, the step response of the response is different from the normal response, which may indicate that there is an abnormality in the device control system. 4. Specific pattern recognition: Identify specific fault modes, such as under certain operating conditions, the operating mode of the device is unstable or similar fault behaviors frequently occur. 5. Abnormal change trend: The change trend of the key parameters of the monitored device is inconsistent with the historical data, which may indicate that the device is in a potential fault state and requires timely intervention and repair. 6. Concentrated occurrence of abnormalities: The frequent occurrence of the same abnormality or failure in the recent period may mean that there is a potential failure risk in a component or system of the equipment.

[0067] These potential abnormal pattern information can be obtained through analysis and feature extraction of equipment operation data, and then applied to abnormal pattern recognition and fault diagnosis, helping maintenance personnel or repair personnel to promptly detect and deal with possible abnormal conditions of the equipment, thereby improving equipment reliability and operating efficiency.

[0068] Specifically, in step 301, the data preprocessing layer is mainly used to preprocess the equipment operation data. Data cleaning: remove noise, outliers or missing values ​​in the data to ensure the integrity and accuracy of the data; data normalization: uniformly scale the data to the same scale range to eliminate the dimensional influence between different data; data smoothing: smooth the data to make the data change more stable, which is conducive to subsequent feature extraction and analysis. In step 302, the fault feature extraction layer extracts various features from the preprocessed equipment operation data and merges them into fault analysis features. Statistical features: such as mean, variance, skewness, kurtosis, etc. describe the statistical properties of data; frequency domain features: extract frequency domain information of data through methods such as Fourier transform; time domain features: analyze based on time series data to extract the characteristics of data changing over time. In step 303, the adaptive control layer dynamically adjusts the model parameters and operation strategies of the abnormal pattern recognition layer according to the real-time monitored equipment status and environmental changes to adapt to different equipment working conditions and fault modes, and ensure the robustness and efficiency of diagnosis. In step 304, the abnormal pattern recognition layer performs pattern recognition on the previously extracted fault analysis features based on the adaptive recognition strategy to obtain potential abnormal pattern information of the target device. In this layer, the features are analyzed through machine learning, pattern matching or other algorithms to identify and define the abnormal patterns of the device and provide accurate fault diagnosis results.

[0069] Through the structures and steps at the above levels, the intelligent fault diagnosis model can comprehensively analyze the equipment operation data, extract fault characteristics, and adaptively adjust the diagnosis strategy according to the real-time situation. Finally, it can realize the abnormal pattern recognition of the target equipment through the abnormal pattern recognition layer, providing accurate and reliable support for equipment maintenance and fault prediction.

[0070] In an optional embodiment, in the above step 303, the model parameters and operation strategies of the abnormal pattern recognition layer are dynamically adjusted according to the real-time monitored device status and environmental changes through the adaptive control layer to adapt to different device working conditions and corresponding failure modes, which can be implemented as follows:

[0071] 401, using a probe detection unit to perform risk probe identification on the device status data and the environment change data to obtain an identification result;

[0072] 402, if the first risk probe exists in the device state data and / or the environment change data, the model learning rate is adjusted to ensure the speed at which the abnormal pattern recognition layer learns the potential abnormal pattern; the first risk probe is used to indicate the phenomenon that the convergence speed does not meet the set threshold when processing certain failure modes; the detection dimension and detection value corresponding to the first risk probe are determined by the target device type;

[0073] 403, if there is a second risk probe in the device status data and / or the environment change data, increase or decrease the number of hidden layer nodes to adapt to the newly added potential abnormal pattern learned by the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the second risk probe are determined by the newly added potential abnormal pattern;

[0074] 404. If a third risk probe exists in the device status data and / or the environmental change data, the number of iterations is dynamically adjusted to improve the robustness of the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the third risk probe are determined by the robustness detection result of the abnormal pattern recognition layer.

[0075] In the embodiment of the present application, a probe detection unit and a risk probe are introduced to dynamically adjust the model parameters and operation strategies of the abnormal pattern recognition layer to adapt to different equipment working conditions and failure modes. The following is a detailed introduction to the probe detection unit, risk probe and corresponding steps:

[0076] The probe detection unit is responsible for monitoring device status data and environmental change data to identify possible risk probes. It can detect based on real-time monitoring data and preset rules or thresholds to indicate whether the parameters and strategies of the abnormal pattern recognition layer need to be adjusted.

[0077] The risk probe is a potential risk identifier identified by the probe detection unit, which is used to indicate the content that needs to be dynamically adjusted to ensure the effectiveness of abnormal pattern recognition. In this embodiment, it includes a first risk probe, a second risk probe and a third risk probe, corresponding to different adjustment dimensions and strategies. In the above step 402, when the first risk probe is detected, the model learning rate of the abnormal pattern recognition layer is adjusted to increase the learning speed to ensure that the potential abnormal pattern can be learned faster. Step 403, when the second risk probe is detected, the number of hidden layer nodes is increased or decreased to adapt to the learned new potential abnormal pattern and improve the model's adaptability. Step 404, when the third risk probe is detected, the number of iterations of the abnormal pattern recognition layer is dynamically adjusted to improve the robustness of the model and ensure accurate identification of the potential abnormal pattern of the device.

[0078] By introducing probe detection units and risk probes, and dynamically adjusting the parameters and strategies of the abnormal pattern recognition layer according to the detection results of different risk probes, it is possible to adapt to changes in equipment working conditions and failure modes more flexibly and efficiently, and improve the accuracy and reliability of abnormal pattern recognition.

[0079] Specifically, in 401, a probe detection unit is used to identify risk probes for device status data and environmental change data. Before obtaining the identification result, the device type in the distributed experimental equipment management and control system can be monitored in real time, and based on the monitoring result, the risk probe type deployed in the probe detection unit can be dynamically adjusted. Then, the dynamically adjusted probe detection unit is sent to different devices or corresponding management and control nodes to achieve real-time monitoring of each device in the distributed experimental equipment management and control system.

[0080] As an optional embodiment, in 304, the abnormal pattern recognition layer performs pattern recognition on the fault analysis feature based on an adaptive recognition strategy to obtain potential abnormal pattern information of the target device, which can be implemented as follows:

[0081] Calculate the probability distribution prediction value of each feature point in the fault analysis feature; based on the probability distribution prediction value, generate a probability distribution prediction map for each feature point and the probability distribution prediction map between each feature point and the surrounding feature points; stack the probability distribution prediction maps between each feature point and the surrounding feature points in three-dimensional space to form a spatial probability distribution prediction network of the fault analysis feature; use an adaptive recognition strategy that matches the type of the target device to adaptively detect the spatial probability distribution prediction network of the fault analysis feature to obtain candidate probability prediction values ​​of potential abnormal patterns in the fault analysis feature; wherein the correspondence between the distribution form of the feature points of the spatial probability distribution prediction network and the type of potential abnormal pattern is determined by a mapping network table pre-input in the adaptive recognition strategy; make a comprehensive decision on the candidate probability prediction values ​​of the potential abnormal pattern to obtain the potential abnormal pattern that matches the target device.

[0082] In the distributed experimental equipment management scenario, the use of abnormal pattern recognition technology can help monitor and diagnose the operating status of each experimental equipment, timely discover potential abnormal behaviors, and improve the reliability and operating efficiency of the equipment. The following is a detailed introduction to the embodiment of this scenario. For the operating data of each experimental equipment, the probability distribution prediction value of the fault analysis feature is first calculated, for example, the distribution of the feature points is predicted by methods such as probability density estimation. Based on the predicted probability distribution value, each feature point and the probability distribution map between them are generated. This map reflects the distribution of the feature points in space, which helps to analyze the correlation between the features. Then, each feature point and its probability distribution map are stacked in three-dimensional space to construct a spatial probability distribution network of the fault analysis feature, showing the distribution and correlation of the features in space. Then, using an adaptive recognition strategy that matches the type of each experimental equipment, the spatial probability distribution network of the fault analysis feature is adaptively detected to identify possible abnormal patterns. Through the pre-input mapping network, the corresponding relationship between the distribution form of the feature points in the spatial probability distribution network and the type of potential abnormal pattern is found. Then, a comprehensive decision is made on the candidate probability prediction value of the potential abnormal pattern, so as to obtain the potential abnormal pattern matched by the target device. The probability distribution, spatial correlation and abnormal pattern detection results of each feature point are comprehensively considered to determine the final abnormal pattern prediction result. Through the implementation of the above steps, the characteristics of each experimental equipment in the distributed experimental equipment management scenario can be analyzed and abnormal patterns can be identified, and the potential abnormal behavior of the equipment can be identified in time, providing important reference for equipment maintenance management and fault prediction, and ensuring the stable operation and safety of the experimental equipment.

[0083] In the embodiment of the present application, the corresponding relationship between the distribution form of the characteristic points of the spatial probability distribution prediction network and the potential abnormal pattern type includes one of the following:

[0084] The concentrated anomaly pattern causes the distribution of feature points in the spatial probability distribution prediction network to be: specific feature point anomalies are concentrated around one or several feature points; the diffuse anomaly pattern causes the distribution of feature points in the spatial probability distribution prediction network to be: specific feature point anomalies are scattered throughout the feature point space; the continuous anomaly pattern causes the distribution of feature points in the spatial probability distribution prediction network to be: specific feature points have continuous abnormal changes; the discontinuous anomaly pattern causes the distribution of feature points in the spatial probability distribution prediction network to be: specific feature points or specific feature point sets have discontinuous anomalies; the clustered anomaly pattern causes the distribution of feature points in the spatial probability distribution prediction network to be: specific feature points present a clustered abnormal pattern in space.

[0085] Specifically, the correspondence between the characteristic point distribution form of the spatial probability distribution prediction network and the potential abnormal pattern type can be determined according to the specific fault analysis characteristics and equipment type. Generally, different types of equipment failures will show certain regularities and correspondences in the distribution form of characteristic points. The following are some possible examples of correspondences:

[0086] Concentrated abnormal pattern: Certain fault modes may cause specific abnormalities to be concentrated around one or several characteristic points, forming a concentrated abnormal pattern. For example, in a vibration signal, a certain frequency component is too high or there is a sudden increase in abnormality.

[0087] Diffuse anomaly pattern: Other failure modes may cause anomalies to be scattered throughout the feature point space, forming a diffuse anomaly pattern. For example, in the temperature change curve, the overall temperature distribution shows irregular changes instead of being concentrated at a certain point.

[0088] Continuous abnormal mode: Some fault modes may be manifested as continuous abnormal changes between characteristic points, forming a continuous abnormal mode. For example, in the current waveform, the current value continues to increase or decrease within a certain period of time.

[0089] Intermittent abnormal mode: Some fault modes may cause intermittent abnormalities in specific feature points or areas, forming intermittent abnormal modes. For example, in spectrum analysis, abnormal values ​​appear intermittently in a certain frequency band.

[0090] Clustered abnormal patterns: Certain fault modes may cause feature points to present clustered abnormal patterns in space. For example, multiple abnormal clusters are formed in the feature point space, each cluster representing a different fault type.

[0091] By analyzing the spatial probability distribution of fault analysis features, predicting the correspondence between the distribution patterns of feature points in the network and the abnormal pattern types, we can provide guidance for adaptive recognition strategies, help identify potential abnormal patterns, and ultimately obtain matching abnormal patterns for target devices. In practical applications, we can design corresponding abnormal pattern recognition strategies based on specific devices and fault types to improve the accuracy and adaptability of the model.

[0092] 103. Based on the potential abnormal pattern, determine the equipment flow control information of the distributed experimental equipment management and control system.

[0093] In the distributed experimental equipment management and control system, the equipment flow control information can be related to the management personnel or the management terminal's authority. These equipment flow control information involve the management personnel's access and operation authority to the experimental equipment and may be affected by potential abnormal behavior.

[0094] In the distributed experimental equipment management and control system, based on the identified potential abnormal patterns, the management system can determine the equipment flow control information according to factors such as the severity of the abnormality and the scope of impact to ensure the safety and normal operation of the experimental equipment. When potential abnormalities are identified in experimental equipment, the system can automatically adjust the permissions of managers, such as limiting the access or operation permissions of specific personnel or teams to equipment that may be affected, to reduce the possibility of further risks and losses. For management terminals in the distributed experimental equipment management system, the system can dynamically adjust their permission settings based on the identified potential abnormal patterns, limit or increase the operating scope of the management terminal to the equipment, and ensure that the equipment is properly managed and controlled under abnormal circumstances. The management and control system will continuously monitor the operating status and abnormal conditions of the experimental equipment, adjust the equipment flow control information at any time according to the latest identification results to adapt to changes in equipment status, and take corresponding measures in a timely manner to ensure the safety and stable operation of the equipment.

[0095] Through the above steps, the experimental equipment management system can identify potential abnormal patterns and promptly determine appropriate equipment flow control information to ensure that management personnel and management terminals can effectively manage and control equipment under abnormal circumstances, thereby improving the efficiency and safety of experimental equipment management.

[0096] 104. Generate abnormal alarm information of the target device based on the device flow control information, and send it to the user at the remote client side.

[0097] 105 . In response to the remote maintenance instruction fed back in response to the abnormal alarm information, execute a remote maintenance operation matching the remote maintenance instruction on the target device.

[0098] In the distributed experimental equipment management scenario, steps 104 and 105 involve the process of generating abnormal alarm information of the target device and implementing remote maintenance operations. These steps are intended to respond to device abnormalities in a timely manner and ensure that remote maintenance instructions are effectively executed. In 104, based on the device flow control information, the system analyzes potential abnormal patterns and generates corresponding abnormal alarm information. This information includes the nature, severity, and scope of impact of the abnormality, so as to notify relevant personnel or systems. The generated abnormal alarm information will be sent to the user on the remote client side to inform them of the possible abnormal conditions of the target device. The user can monitor and track the device status in real time through the client so that the necessary measures can be taken in time to respond to the abnormal situation. In 105, after receiving the abnormal alarm information, the user on the remote client side will formulate a remote maintenance instruction according to the specific situation and send it to the management system. The management system performs remote maintenance operations matching the instructions on the target device based on the received remote maintenance instructions. This may include restarting the device, remote diagnosis, remote calibration, and other operations to resolve device abnormalities or failures. After performing the remote maintenance operation, the system will feedback the operation execution results to the user on the remote client side so that the user can understand the effect of the operation and the change in the device status.

[0099] Through steps 104 and 105, the distributed experimental equipment management system can generate corresponding alarm information and perform effective remote maintenance operations when an equipment anomaly is found. This can improve the efficiency of equipment fault handling, reduce maintenance costs, ensure the continuous and stable operation of the equipment, and at the same time strengthen the interaction and real-time monitoring capabilities between users and equipment, thereby improving overall operating efficiency and safety.

[0100] In an embodiment of the present application, in response to the monitoring instruction of the distributed experimental equipment control system, the equipment operation data of the target equipment in the distributed experimental equipment control system is obtained. Here, a data basis is provided for subsequent intelligent detection and remote maintenance, which helps to timely discover potential abnormal patterns and warn possible problems in advance, thereby reducing the occurrence of equipment failures and reducing maintenance costs. Then, the equipment operation data is input into the fault intelligent diagnosis model to perform abnormal pattern recognition of the target equipment to obtain the potential abnormal pattern matching the target equipment. In this way, the process and control strategy of the equipment can be automatically adjusted based on the abnormal pattern to reduce the risk of failure and improve equipment utilization and efficiency. Then, based on the potential abnormal pattern, the equipment flow control information of the distributed experimental equipment control system is determined. This helps to improve the accuracy and reliability of potential abnormal pattern recognition and reduce the influence of subjective factors on equipment management and maintenance. Furthermore, abnormal alarm information of the target equipment is generated based on the equipment flow control information and sent to the user on the remote client side. Finally, in response to the remote maintenance instruction fed back to the abnormal alarm information, a remote maintenance operation matching the remote maintenance instruction is performed on the target equipment. Abnormal conditions can be obtained in time and corresponding measures can be taken to improve the reliability and safety of equipment operation. At the same time, responding to remote maintenance instructions and performing remote maintenance operations can effectively reduce maintenance response time and improve maintenance efficiency. In the embodiment of the present application, through the operation of intelligent fault diagnosis model, equipment flow control and remote maintenance, it is helpful to realize the intelligent and real-time management of the distributed experimental equipment management and control system, improve the remote maintenance efficiency of distributed experimental equipment, timely discover potential risk patterns in the system, reduce system operation risks, enhance system stability and reliability, reduce maintenance costs, and provide users with better user experience and service support.

[0101] In another embodiment of the present application, a distributed experimental equipment management and control system is provided, wherein the distributed experimental equipment management and control system is used to operate and manage experimental equipment, wherein the experimental equipment includes different types of equipment, see Figure 2 The distributed experimental equipment management and control system includes the following units:

[0102] A monitoring unit, configured to obtain device operation data of a target device in the distributed experimental device control system in response to a monitoring instruction for the distributed experimental device control system;

[0103] an identification unit configured to input the device operation data into a fault intelligent diagnosis model to perform abnormal pattern identification on the target device to obtain a potential abnormal pattern matching the target device;

[0104] A circulation unit, configured to determine the equipment circulation control information of the distributed experimental equipment management and control system based on the potential abnormal mode;

[0105] an alarm unit, configured to generate abnormal alarm information of a target device based on the device flow control information, and send the information to a user at a remote client side;

[0106] The maintenance unit is configured to respond to the remote maintenance instruction fed back to the abnormal alarm information and execute a remote maintenance operation matching the remote maintenance instruction on the target device.

[0107] Further optionally, the monitoring unit, in response to a monitoring instruction for the distributed experimental equipment management and control system, obtains the equipment operation data of the target equipment in the distributed experimental equipment management and control system, and is configured to:

[0108] Acquire the experimental tasks matched by the target device in the distributed experimental equipment management and control system; wherein the experimental tasks matched by different types of devices have different task requirements;

[0109] Based on the task requirements of the target device, a device remote control task corresponding to the target device is constructed through a dynamic control model; wherein the device remote control task is used to assist the target device in achieving the experimental task;

[0110] Synchronizing the device remote control task to the target device in the distributed experimental device control system, and receiving the monitoring instruction generated by the target device in response to the device remote control task;

[0111] Based on the monitoring instructions, the device operation data of the target device during the execution of the experimental task is collected in real time.

[0112] Further optionally, the dynamic management and control model includes at least the following structures: a feature recognition layer, a feature fusion layer, and a dynamic construction layer;

[0113] The monitoring unit, based on the task requirements of the target device, constructs a device remote control task corresponding to the target device through a dynamic control model, and is configured as follows:

[0114] Through the feature recognition layer, the operation and maintenance requirement features of the target device are extracted from the task requirements of the target device;

[0115] Through the feature fusion layer, multi-dimensional feature fusion and conflict detection are performed on the operation and maintenance demand features of the target equipment to obtain the comprehensive operation and maintenance features of the target equipment;

[0116] Through the feature fusion layer, based on the pre-established control task components and the spatial mapping relationship between the task components and the demand dimensions, the comprehensive operation and maintenance characteristics of the target device are dynamically constructed to obtain the remote control tasks of the target device.

[0117] Further optionally, the intelligent fault diagnosis model includes at least the following structures: a data preprocessing layer, a fault feature extraction layer, an adaptive control layer, and an abnormal pattern recognition layer;

[0118] The identification unit inputs the device operation data into the fault intelligent diagnosis model to perform abnormal pattern identification on the target device to obtain a potential abnormal pattern matching the target device, and is configured to:

[0119] Preprocessing the equipment operation data through a data preprocessing layer; the preprocessing includes at least: data cleaning, data normalization, and data smoothing;

[0120] Through the fault feature extraction layer, statistical features, frequency domain features, and time domain features are extracted from the equipment operation data, and are integrated into fault analysis features;

[0121] Through the adaptive control layer, the model parameters and operation strategies of the abnormal pattern recognition layer are dynamically adjusted according to the real-time monitoring of equipment status and environmental changes to adapt to different equipment working conditions and corresponding failure modes;

[0122] Through the abnormal pattern recognition layer, pattern recognition is performed on the fault analysis features based on an adaptive recognition strategy to obtain potential abnormal pattern information of the target device; the potential abnormal pattern information is used to indicate candidate abnormal behaviors existing in the target device.

[0123] Further optionally, the recognition unit dynamically adjusts the model parameters and operation strategies of the abnormal pattern recognition layer through the adaptive control layer according to the real-time monitored device status and environmental changes to adapt to different device working conditions and corresponding failure modes, and is configured as follows:

[0124] Use the probe detection unit to perform risk probe identification on the equipment status data and environmental change data to obtain the identification results;

[0125] If the first risk probe exists in the device status data and / or the environmental change data, the model learning rate is adjusted to ensure the speed at which the abnormal pattern recognition layer learns the potential abnormal pattern; the first risk probe is used to indicate the phenomenon that the convergence speed does not meet the set threshold when processing certain failure modes; the detection dimension and detection value corresponding to the first risk probe are determined by the target device type;

[0126] If there is a second risk probe in the device status data and / or the environmental change data, the number of hidden layer nodes is increased or decreased to adapt to the newly added potential abnormal pattern learned by the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the second risk probe are determined by the newly added potential abnormal pattern;

[0127] If there is a third risk probe in the device status data and / or environmental change data, the number of iterations is dynamically adjusted to improve the robustness of the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the third risk probe are determined by the robustness detection result of the abnormal pattern recognition layer.

[0128] Further optionally, the identification unit, before using the probe detection unit to perform risk probe identification on the device status data and the environment change data to obtain the identification result, is further configured as follows:

[0129] Performing real-time monitoring of the equipment types in the distributed experimental equipment management and control system, and dynamically adjusting the risk probe types deployed in the probe detection unit based on the monitoring results;

[0130] The dynamically adjusted probe detection unit is sent to different devices or corresponding control nodes to achieve real-time monitoring of each device in the distributed experimental equipment control system.

[0131] Further optionally, the recognition unit performs pattern recognition on the fault analysis feature based on an adaptive recognition strategy through an abnormal pattern recognition layer to obtain potential abnormal pattern information of the target device, and is configured as follows:

[0132] Calculate the probability distribution prediction value of each feature point in the fault analysis feature;

[0133] Based on the probability distribution prediction value, generate a probability distribution prediction map of each feature point and its relationship with surrounding feature points;

[0134] Stacking the probability distribution prediction maps of each feature point and the surrounding feature points in three-dimensional space to form a spatial probability distribution prediction network of the fault analysis feature;

[0135] Adopting an adaptive recognition strategy that matches the type of the target device, the spatial probability distribution prediction network of the fault analysis feature is adaptively detected to obtain candidate probability prediction values ​​of potential abnormal patterns in the fault analysis feature; wherein the correspondence between the distribution form of the feature points of the spatial probability distribution prediction network and the type of potential abnormal patterns is determined by a mapping network table pre-input in the adaptive recognition strategy;

[0136] A comprehensive decision is made on the candidate probability prediction values ​​of the potential abnormal patterns to obtain the potential abnormal patterns matched by the target device.

[0137] Further optionally, the corresponding relationship between the distribution form of the feature points of the spatial probability distribution prediction network and the potential abnormal pattern type is:

[0138] The concentrated anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: specific feature point anomalies are concentrated around one or several feature points;

[0139] The diffuse anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: specific feature points are abnormally scattered throughout the feature point space;

[0140] The continuous abnormal pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: there are continuous abnormal changes between specific feature points;

[0141] The discontinuous anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: discontinuous anomalies occur at specific feature points or a specific set of feature points;

[0142] The clustering anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network: specific feature points present a clustered anomaly pattern in space.

[0143] In the embodiments of the present application, through intelligent fault diagnosis models, equipment flow control, and remote maintenance operations, it helps to realize the intelligent and real-time management of the distributed experimental equipment control system, improve the remote maintenance efficiency of distributed experimental equipment, timely discover potential risk patterns in the system, reduce system operation risks, enhance system stability and reliability, reduce maintenance costs, and provide users with better user experience and service support.

[0144] In another embodiment of the present application, an intelligent computing platform is further provided, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0145] Memory, used to store computer programs;

[0146] The processor is used to implement the remote maintenance method based on distributed experimental equipment described in the method embodiment when executing the program stored in the memory.

[0147] The communication bus 1140 mentioned in the above electronic device may be a peripheral component interconnection standard

[0148] (Peripheral Component Interconnect, PCI) bus or extended industry standard architecture

[0149] (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc.

[0150] The embodiment of the present application provides a remote maintenance method based on distributed experimental equipment for constructing a low-energy computing unit.

[0151] For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0152] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0153] The memory 1130 may include a random access memory (RAM) or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0154] The above-mentioned processor 1110 can be a general-purpose processor, including an artificial intelligence processor, a graphics processing unit (GPU), an artificial intelligence processor card (Machine Learning Unit, MLU), a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0155] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement each step that can be executed by an electronic device in the above method embodiment.

Claims

1. A remote maintenance method based on distributed experimental equipment, characterized in that: Applied to a distributed experimental equipment management and control system, the distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment; the method includes: In response to a monitoring instruction for the distributed experimental equipment control system, obtaining equipment operation data of a target equipment in the distributed experimental equipment control system; Inputting the equipment operation data into the fault intelligent diagnosis model to perform abnormal pattern recognition on the target equipment to obtain potential abnormal patterns matching the target equipment; Based on the potential abnormal pattern, determine the equipment flow control information of the distributed experimental equipment management and control system; Generate abnormal alarm information of the target device based on the device flow control information, and send it to the user on the remote client side; In response to the remote maintenance instruction fed back in response to the abnormal alarm information, a remote maintenance operation matching the remote maintenance instruction is performed on the target device.

2. The remote maintenance method based on distributed experimental equipment according to claim 1 is characterized in that: The step of obtaining the device operation data of the target device in the distributed experimental device management and control system in response to the monitoring instruction of the distributed experimental device management and control system includes: Acquire the experimental tasks matched by the target device in the distributed experimental equipment management and control system; wherein the experimental tasks matched by different types of devices have different task requirements; Based on the task requirements of the target device, a device remote control task corresponding to the target device is constructed through a dynamic control model; wherein the device remote control task is used to assist the target device in achieving the experimental task; Synchronizing the device remote control task to the target device in the distributed experimental device control system, and receiving the monitoring instruction generated by the target device in response to the device remote control task; Based on the monitoring instructions, the device operation data of the target device during the execution of the experimental task is collected in real time.

3. The remote maintenance method based on distributed experimental equipment according to claim 2 is characterized in that: The dynamic management and control model at least includes the following structures: feature recognition layer, feature fusion layer, and dynamic construction layer; The device remote control task corresponding to the target device is constructed based on the task requirements of the target device through the dynamic control model, including: Through the feature recognition layer, the operation and maintenance requirement features of the target device are extracted from the task requirements of the target device; Through the feature fusion layer, multi-dimensional feature fusion and conflict detection are performed on the operation and maintenance demand features of the target equipment to obtain the comprehensive operation and maintenance features of the target equipment; Through the feature fusion layer, based on the pre-established control task components and the spatial mapping relationship between the task components and the demand dimensions, the comprehensive operation and maintenance characteristics of the target device are dynamically constructed to obtain the remote control tasks of the target device.

4. The remote maintenance method based on distributed experimental equipment according to claim 1 is characterized in that: The fault intelligent diagnosis model at least includes the following structures: data preprocessing layer, fault feature extraction layer, adaptive control layer, abnormal pattern recognition layer; The step of inputting the device operation data into the fault intelligent diagnosis model to perform abnormal pattern recognition on the target device to obtain a potential abnormal pattern matching the target device includes: Preprocessing the equipment operation data through a data preprocessing layer; the preprocessing includes at least: data cleaning, data normalization, and data smoothing; Through the fault feature extraction layer, statistical features, frequency domain features, and time domain features are extracted from the equipment operation data, and are integrated into fault analysis features; Through the adaptive control layer, the model parameters and operation strategies of the abnormal pattern recognition layer are dynamically adjusted according to the real-time monitoring of equipment status and environmental changes to adapt to different equipment working conditions and corresponding failure modes; Through the abnormal pattern recognition layer, pattern recognition is performed on the fault analysis features based on an adaptive recognition strategy to obtain potential abnormal pattern information of the target device; the potential abnormal pattern information is used to indicate candidate abnormal behaviors existing in the target device.

5. The remote maintenance method based on distributed experimental equipment according to claim 4 is characterized in that: The adaptive control layer dynamically adjusts the model parameters and operation strategies of the abnormal pattern recognition layer according to the real-time monitored equipment status and environmental changes to adapt to different equipment working conditions and corresponding failure modes, including: Use the probe detection unit to perform risk probe identification on the equipment status data and environmental change data to obtain the identification results; If the first risk probe exists in the device status data and / or the environmental change data, the model learning rate is adjusted to ensure the speed at which the abnormal pattern recognition layer learns the potential abnormal pattern; the first risk probe is used to indicate the phenomenon that the convergence speed does not meet the set threshold when processing certain failure modes; the detection dimension and detection value corresponding to the first risk probe are determined by the target device type; If there is a second risk probe in the device status data and / or the environmental change data, the number of hidden layer nodes is increased or decreased to adapt to the newly added potential abnormal pattern learned by the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the second risk probe are determined by the newly added potential abnormal pattern; If there is a third risk probe in the device status data and / or environmental change data, the number of iterations is dynamically adjusted to improve the robustness of the abnormal pattern recognition layer; the detection dimension and detection value corresponding to the third risk probe are determined by the robustness detection result of the abnormal pattern recognition layer.

6. The remote maintenance method based on distributed experimental equipment according to claim 5 is characterized in that: Before the probe detection unit is used to perform risk probe identification on the device status data and the environment change data to obtain the identification result, the method further includes: Performing real-time monitoring of the equipment types in the distributed experimental equipment management and control system, and dynamically adjusting the risk probe types deployed in the probe detection unit based on the monitoring results; The dynamically adjusted probe detection unit is sent to different devices or corresponding control nodes to achieve real-time monitoring of each device in the distributed experimental equipment control system.

7. The remote maintenance method based on distributed experimental equipment according to claim 4 is characterized in that: The abnormal pattern recognition layer performs pattern recognition on the fault analysis feature based on an adaptive recognition strategy to obtain potential abnormal pattern information of the target device, including: Calculate the probability distribution prediction value of each feature point in the fault analysis feature; Based on the probability distribution prediction value, generate a probability distribution prediction map of each feature point and its relationship with surrounding feature points; Stacking the probability distribution prediction maps of each feature point and the surrounding feature points in three-dimensional space to form a spatial probability distribution prediction network of the fault analysis feature; Adopting an adaptive recognition strategy that matches the type of the target device, the spatial probability distribution prediction network of the fault analysis feature is adaptively detected to obtain candidate probability prediction values ​​of potential abnormal patterns in the fault analysis feature; wherein the correspondence between the distribution form of the feature points of the spatial probability distribution prediction network and the type of potential abnormal patterns is determined by a mapping network table pre-input in the adaptive recognition strategy; A comprehensive decision is made on the candidate probability prediction values ​​of the potential abnormal patterns to obtain the potential abnormal patterns matched by the target device.

8. The remote maintenance method based on distributed experimental equipment according to claim 7 is characterized in that: The correspondence between the distribution form of the characteristic points of the spatial probability distribution prediction network and the potential abnormal pattern type includes: The concentrated anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: specific feature point anomalies are concentrated around one or several feature points; The diffuse anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: specific feature points are abnormally scattered throughout the feature point space; The continuous abnormal pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: there are continuous abnormal changes between specific feature points; The discontinuous anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network as follows: discontinuous anomalies occur at specific feature points or a specific set of feature points; The clustering anomaly pattern leads to the distribution of feature points in the spatial probability distribution prediction network: specific feature points present a clustered anomaly pattern in space.

9. A distributed experimental equipment management and control system, characterized in that: The distributed experimental equipment management and control system is used to operate and manage experimental equipment, and the experimental equipment includes different types of equipment. The distributed experimental equipment management and control system includes: A monitoring unit, configured to obtain device operation data of a target device in the distributed experimental device control system in response to a monitoring instruction for the distributed experimental device control system; an identification unit configured to input the device operation data into a fault intelligent diagnosis model to perform abnormal pattern identification on the target device to obtain a potential abnormal pattern matching the target device; A circulation unit, configured to determine the equipment circulation control information of the distributed experimental equipment management and control system based on the potential abnormal mode; an alarm unit, configured to generate abnormal alarm information of a target device based on the device flow control information, and send the information to a user at a remote client side; The maintenance unit is configured to respond to the remote maintenance instruction fed back to the abnormal alarm information and execute a remote maintenance operation matching the remote maintenance instruction on the target device.

10. An intelligent computing platform, characterized in that: The intelligent computing platform includes: at least one processor, memory, and input-output unit; In which, the memory is used to store computer programs, the processor is used to call the computer program stored in the memory to execute the remote maintenance method based on distributed experimental equipment as described in any one of claims 1 to 8, and the input and output unit is used to receive user input and display output information of the computer program stored in the memory.

Images